Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    init

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Disconnect
    -0.07
     ConcurrentHashMap
    -0.07
     OK
    -0.06
    Locator
    -0.06
     RecyclerView
    -0.06
    未必
    -0.06
     skull
    -0.06
     seaborn
    -0.06
    回忆
    -0.06
    Pragma
    -0.06
    POSITIVE LOGITS
    떳
    0.07
    PERT
    0.07
     зависит
    0.07
    消耗
    0.07
    もらえ
    0.07
    esus
    0.07
    هدف
    0.07
     erotik
    0.07
    ₊
    0.06
    完善的
    0.06
    Act Density 0.005%

    No Known Activations